INDEX

Explanations

phrases and words related to consequences and reasons for actions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

icontrol

-0.15

orrow

-0.14

nees

-0.14

 kern

-0.14

 braces

-0.14

ìĸ´

-0.14

atching

-0.14

ounsel

-0.14

ushi

-0.13

 borrowing

-0.13

POSITIVE LOGITS

.uml

0.16

rage

0.16

Ã³Å¼

0.15

gere

0.15

zones

0.14

unge

0.14

.codes

0.14

iske

0.14

attro

0.14

_toolbar

0.14

Activations Density 0.203%

phrases and words related to consequences and reasons for actions

No Comments

No Known Activations